Re-defining Humor Data Objects for AI Humor Research

2026-05-24

AI Summary

This study addresses the limitations of traditional AI approaches to humor, which often reduce it to binary classification and overlook its contextual dependence and interpretive demands in social interaction. The work proposes reconceptualizing humor as a socially situated communicative act and introduces a novel data construct for humor reasoning that integrates contextual, multimodal, and transcript-based information. Building on large language models (LLMs), the authors develop an iterative prompting and data synthesis strategy that substantially enhances the quality and applicability of generated humor explanations. This approach significantly reduces critical errors and yields a large corpus of high-quality explanatory data, thereby establishing a foundational framework for AI systems to understand humor as a form of social behavior.

Abstract

In most existing AI humor research, humor was treated as either "present" or "not present." We explore the concept of humor as a social interaction with context and explanations. During this project, we defined a humor reasoning data object and developed a way to prompt LLMs to generate an explanation of humor effective for general population. We iterated from an earlier prompt to an improved prompt, found that the later version reduced important errors, and then scaled generation to a large number of data objects which have the potential to enable data synthesis and data augmentation for AI humor research. Our main takeaway is that better prompting of an LLM improves humor explanation quality, especially by handling missing context, multi-modality, and transcript issues more carefully. These results establish a strong foundation for future work on AI understanding of humor as social behavior.

Problem

• AI humor research
• humor as social interaction
• contextual understanding
• humor explanation
• data object definition

Innovation

• humor reasoning
• prompt engineering
• large language models
• context-aware humor
• data augmentation